Towards robot software abstraction: ROS 2-based framework for object handling within a robot cell

Abstract

Recent advancements in industrial automation have led to the development of increasingly adaptable and reconfigurable systems, driven by the necessity for flexibility and efficiency in manufacturing. This paper introduces a ROS 2-based software framework tailored for object handling within a robot cell, addressing challenges pertaining to reconfigurability, modularity, and interoperability. The proposed solution simplifies the deployment process of robotic applications and provides a standardized ROS 2-based platform, making it particularly beneficial for small and medium automation enterprises that require frequent reprogramming and adaptation of robot cells to different settings. By ensuring software and hardware agnosticism, the framework presents a comprehensive pipeline for designing, developing, and deploying object pick-and-place applications, demonstrated through an automated kitting use-case where a robot sorts industrial spare parts from a conveyor belt using a simple camera. The system integrates real-time object detection and classification capabilities with ROS 2 to facilitate effective communication between perception and robot action. This research advocates for open-source solutions and collaboration, aiming to enhance the adaptability and efficiency of robotic solutions across diverse industrial applications.